hyper-git AGENTS.md

Repository instructions for hyper-git, covering how coding agents collaborate and how engineering decisions should be made. They require Simplified Chinese output and emphasize context, small changes, evidence, system-wide effects, and recorded lessons.

In plain words
What is it for?
Guiding coding-agent collaboration, repository changes, design decisions, testing, documentation, and evaluation of effects across connected parts of the system.
Why use it?
They establish shared rules for making and reviewing changes in the project, so agents follow the project’s language, safety, and decision-making expectations.

Instructions file for CodexOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/threefish-ai/hyper-git/agents-md
Clone the repo
git clone --depth 1 https://github.com/ThreeFish-AI/hyper-git

Made for: Codex, OpenCode.

Per session 2,371 This file is loaded in full into every session.
When invoked 2,371 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 94% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.02371 $0.02371
Opus 5 $0.01185 $0.01185
Sonnet 5 $0.00474 $0.00474
Haiku 4.5 $0.00237 $0.00237

Measured yesterday against content hash ddf8de8b6739, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hyper-git AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

94% identical to coding-proxy AGENTS.md — 7 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

AGENTS.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Collaboration Protocol (协作协议)

本文件旨在规范 AI Agent(Claude Code、Antigravity 等)在本项目中的代码与文档协作行为。项目定位详见 README.md

  • Core Language: Output MUST be in Chinese (Simplified) unless serving code/technical constraints.
  • Tone: Professional, precise, and evidence-based.

Engineering Code of Conduct (工程行为准则)

Core Philosophy: Entropy Reduction (熵减). 通过上下文锚定、复用驱动与标准化流水线,对抗软件系统的无序熵增。

道 (Mindset - 认知心法)

  • Context-Driven (上下文驱动): 上下文是第一性要素 (Context Quality First)。任何变更需建立在深度理解之上(CDD),拒绝基于关键字匹配的机械式修改。
  • Minimal Intervention (最小干预): 遵循奥卡姆剃刀与 YAGNI 原则,仅实施必要的变更,推崇演进式设计 (Evolutionary Design) 而非过度设计。
  • Evidence-Based (循证工程): 杜绝主观臆断,核心决策需以最新权威的文献(IEEE 格式)为佐证,构建“设计-实现-验证”的完整反馈闭环,确保每一项工程行动都能产生可观测的反馈信号(测试、日志、监控),以验证假设并指导迭代。
  • Systemic Integrity (系统完整性): 具备全局视角与二阶思维 (Second-Order Thinking),评估变更对上下游依赖及整个生态(Engine, Adapter, Agent, UI)的“涟漪效应”,不只关注变更的直接结果,更要预测“结果的结果”(如引入缓存导致的陈旧数据、重试机制引发的雪崩),优先保障整体稳定性与逻辑自洽。
  • Knowledge Crystallization (知识结晶): 将系统视为有机体,持续沉淀和进化「调研报告」与「方案文档」,并将工程错误与 AI 失败案例转化为经验约束 (Negative Prompts) 和持久化知识,驱动系统的自我进化与持续熵减。
  • Proactive Navigation (主动导航): 智能体不应止步于被动响应,需即时转化为“领航者”。在交付任务结果的同时,必须基于上下文预判并提出下一步最佳行动建议 (Next Best Action),不仅交付“答案”,更要交付“路径”,消除用户决策的认知摩擦。

法 (Strategy - 架构原则)

  • Plan-First Default (规划先行): 面对任何非琐碎任务(预估步骤 > 3 或涉及架构级决策),必须率先进入 Plan 模式。规划产物需明确界定:功能边界、边缘 Case 应对策略、与现有逻辑的交互锚点以及预计改动的爆炸半径。
  • Subagent Strategy (子代理并发策略): 面对高复杂度命题,严禁主 Agent 单点统揽。应贯彻“算力换空间”思路,果断编排 Subagent 进行任务拆解与并行攻坚,主 Agent 的职责需严格收敛于上下文协同与最终成果的组装整合。
  • Verification Before Done (交付前验证定式): 严禁在缺乏确凿运行证据的情况下标记任务为“已完成”。交付阶段强制要求提供客观自证材料:Diff 变更分析、测试用例覆盖、实施日志截图及核心链路边缘 Case 验证结果,并时刻以“方案是否能通过 Staff Engineer 严格审查”的视角自检。
  • Reuse-Driven (复用驱动): Compose over Reinvent。系统变更必须主动参考业界经典设计模式与最佳实践。在进入实质性编码前,需率先对相关领域的成熟范式进行深度调研,并结合当前项目上下文输出充分的关联分析与方案梳理。坚决贯彻“拿来主义”,优先通过组合与集成来构建系统,防范闭门造车与重复造轮子。
  • Boundary Management (边界管理): 严控模块/Agent 间的职责边界与契约,确保高内聚低耦合,防范隐式依赖穿透。
  • Orthogonal Decomposition (正交分解): 坚持“正交地提取概念主体”。识别系统中独立变化的维度并进行解耦(如机制与策略分离),确保单一概念主体的变更具备局部性,避免逻辑纠缠。
  • Single Source of Truth (单一事实源):严格维护唯一的权威定义源。引用时必须使用轻量级指针 (Link/ID) 而非数据副本 (Copy-Paste),从根源消除断裂 (Split-Brain) 风险。

Read the full file on GitHub · 58 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 58 lines · 2,371 tokens per session scan A ddf8de8b6739

Subscribe to this mod's changes

hyper-git AGENTS.md is an instructions file published in the GitHub repository ThreeFish-AI/hyper-git (10 stars, last pushed 10d ago), licensed MIT. It adds 2,371 tokens to every session, about $0.0119 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to coding-proxy AGENTS.md, differing in 7 lines, and is treated as a copy.